Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 2803
    Prev
    Next
    INDEX
    Explanations

    versions and compatibility specifications in software dependency configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     InputDecoration
    -1.01
     متعلقه
    -0.77
     JAXBElement
    -0.63
    حياته
    -0.62
    WriteLiteral
    -0.61
    Usual
    -0.60
    InputTagHelper
    -0.60
    ()?;
    -0.59
     Réponses
    -0.58
    Composable
    -0.58
    POSITIVE LOGITS
     version
    0.95
     getVersion
    0.94
    version
    0.85
     Version
    0.85
    Version
    0.84
     versions
    0.81
     AssemblyVersion
    0.78
     Versions
    0.77
     VERSION
    0.75
    VERSION
    0.74
    Activations Density 0.410%

    No Known Activations